Relatedly, I've been working on discovering search ranking algorithms. Starting with a primitive, what can an agent do to generate search ranking + query understanding code that best optimizes a ground truth:
https://softwaredoug.com/blog/2025/10/19/agentic-code-genera...
Neat, thanks for the link! Seems like the agent feedback loop made a big difference for your use case. Would be interesting to see how much of a difference more advanced methods (like the genetic algs you mentioned) would make